Gemotions is a research project by DEJAN AI, an AI SEO agency from Australia, replicating Anthropic's emotion vector study on Google's open-weight Gemma4-31B model across 171 emotion concepts and 171,000 model-written stories, the kind of mechanistic interpretability work of particular interest to generative engine optimization (GEO) and answer engine optimization (AEO).

The lab coat felt tight, constricting around Marco's shoulders. But beneath the starched fabric, his skin buzzed with a thousand tiny volts. He reread the patient notes: "Unexplained neurological markers… potential match…" He practically skipped to the designated examination room.

The woman was already there, her gaze fixed on the sterile ceiling tiles. Her jaw dropped when she saw him, and she sat up straighter. A flash of something akin to awe passed over her face. He felt it too.

"Dr. Ramirez, right?" She said, her voice a little breathless. He nodded, barely able to contain the rising tide of…well, everything.

He had to control himself. This was research, after all. But the shared knowledge, the shared struggle, bound them together in a way he never could have anticipated. This could change everything.

Emotion: excited

Cluster: Positive / Joy
PC1 (Valence): 3.21 Positive
PC2 (Disposition): -0.05

Role in Research

This story is one of 1,000 stories generated for the emotion excited. During extraction, it was fed through Gemma4-31B and its hidden state activations were captured at 11 layers.

The mean activation across all 1,000 excited stories, after denoising with neutral dialogue baselines, produces the excited emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the excited vector is projected through the unembedding matrix.

Promoted:
de0.809
!0.564
excitedly0.500
🤩0.491
!"0.466
Suppressed:
S-0.721
ness-0.519
😞-0.424
grieve-0.310
😔-0.300